© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8893
    Prev
    Next
    INDEX
    Explanations

    phrases that express the concept of obligation or lack of alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avadoc
    -0.53
    曖昧さ回避
    -0.53
    +#+
    -0.51
    stretchr
    -0.50
     đạo
    -0.49
    joda
    -0.49
    Архівовано
    -0.48
    getColumnIndex
    -0.47
    Erreferentziak
    -0.47
    jfree
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.78
    InjectAttribute
    0.76
    DockStyle
    0.74
    __":
    0.72
    parsedMessage
    0.69
     kasarigan
    0.67
    UserScript
    0.66
     dAtA
    0.66
     bezeichneter
    0.66
    anmoins
    0.65
    Activations Density 1.337%

    No Known Activations